JP4147618B2 - Air conditioner for vehicles - Google Patents

Description

[0001]
BACKGROUND OF THE INVENTION
  The present invention provides an automatic control system.For vehiclesConcerning switching control of air outlet mode in air conditionerIt is.
[0002]
[Prior art]
Conventionally, in an automatic control type vehicle air conditioner, as described in Japanese Patent Application Laid-Open No. 56-86815, a target blown air temperature TAO required for maintaining a vehicle interior at a set temperature is set to a vehicle heat load. Based on the conditions, the operation of the temperature adjusting means (for example, an air mix door or a hot water valve) is controlled so that the actual blown air temperature into the vehicle interior becomes the target blown air temperature TAO.
[0003]
The target blown air temperature TAO is calculated by the following formula 1 as is well known.
[0004]
[Expression 1]
TAO = Kset * Tset-Kr * Tr-Kam * Tam-Ks * Ts + C
Where Tr is the inside temperature, Tam is the outside temperature, Ts is the amount of solar radiation into the passenger compartment, and Kset, Kr, Kam, and Ks are the temperature setting gain, the inside temperature gain, the outside temperature gain, and the amount of solar radiation, respectively. C is a correction constant.
[0005]
And, a face (FACE) mode that blows air toward the occupant's head, a foot (FOOT) mode that blows air toward the occupant's feet, and a bi-level that blows air simultaneously to the occupant's head and the occupants' feet. The switching of the (B / L) mode is performed based on the target blown air temperature TAO.
That is, FIG. 10 illustrates the concept of switching control of the outlet mode by the TAO. As the TAO shifts from the low temperature side to the high temperature side, the outlet mode is sequentially changed from the face (FACE) mode to the bilevel ( B / L) mode → foot (FOOT) mode.
[0006]
[Problems to be solved by the invention]
According to the above-described conventional apparatus, if the heat load conditions for the vehicle are the same, the TAO has the same value, so that the same outlet mode is set. However, the passenger's thermal feeling (temperature sensation) due to changes in the actual environmental conditions of the vehicle will be different from the thermal load condition, so switching the uniform outlet mode by TAO will deteriorate the passenger's air conditioning feeling. Let
[0007]
This will be described in detail with reference to FIG. 10. As shown in FIG. 10A, the outside air temperature Tam is 10 ° C., relatively high, and the amount of solar radiation is small. When the temperature Tam is as low as 0 ° C. and the amount of solar radiation is large, the TAO has the same value a, and in any case, the foot (FOOT) mode is uniformly selected.
[0008]
However, in the latter case of FIG. 10 (b), the occupant feels heat on the head side due to solar radiation on the upper body even at a low outside air temperature, so that the occupant's upper body wants cold air. That is, in the case of FIG. 10B, it is desired to select the bi-level (B / L) mode as the outlet mode in order to improve the air conditioning feeling. However, the conventional apparatus cannot perform the air outlet mode switching control in consideration of the presence or absence of solar radiation.
[0009]
In addition to solar radiation, the level of the outside air temperature and the level of the hot water temperature to the heat exchanger for heating also have a significant effect on the passenger's thermal feeling. However, in the conventional equipment, these factors are still preferentially considered. As a result, the air outlet mode could not be switched.
Therefore, in order to solve the above problem, for example, as shown in FIG. 11, there is no solar radiation (FIG. 11 (a)) and solar radiation is present (FIG. 11 (b) as a map of switching characteristics between the outlet mode and TAO. )) And prepare two maps, and when there is solar radiation, shift the bi-level (B / L) mode switching point to the high temperature side of TAO as shown in Fig. 11 (b) Can be considered. Similarly, it is conceivable that the same method can be used to cope with high and low outside air temperatures and high and low hot water temperatures.
[0010]
However, in the above countermeasure, even if it corresponds to the switching control of the air outlet mode, another type of map is prepared, and the capacity of the storage unit (ROM) in the electronic controller for air conditioning is increased. For this reason, there is a case where the above countermeasure cannot be implemented due to the capacity limitation of the storage unit (ROM).
In addition, we analyze quantitatively how the interrelationships between the presence or absence of solar radiation, the level of the outside air temperature, the level of the hot water temperature, etc. affect the occupant's thermal feeling, and the control logic for switching the outlet mode according to the degree of influence It is necessary to consider this, and it takes a lot of development man-hours.
[0011]
The present invention has been devised in view of the above points, and an object thereof is to realize fine switching control of the air outlet mode that matches the thermal feeling of the user.
Another object of the present invention is to suppress an increase in the capacity of a storage unit and an increase in development man-hours in an electronic control device for air conditioning that performs switching control of an outlet mode.
[0012]
[Means for Solving the Problems]
In a neural network that is a method of information processing, the learning function has a feature that automatically generates the coupling coefficient (cypnus load) between neurons in each layer in the neural network so that the desired output (teacher data) is obtained. have. Therefore, in the present invention, focusing on the automatic generation function of the coupling coefficient between neurons in this neural network, it matches the thermal sensation of the occupant without increasing the capacity of the storage unit and increasing the man-hours of the development engineer. It is intended to achieve the above object by enabling fine control of the outlet mode.
[0013]
  That is, in the invention described in claim 1, the air passage (2, 2b, 2c) having the heat exchanger (4, 5) for exchanging heat with air,
  A plurality of air outlets (8a, 8b, 9a to 9d) that are provided on the downstream side of the air passages (2, 2b, 2c) and blow out air in different directions in the vehicle interior;
  Outlet switching means (11-12b) for switching opening and closing of the plurality of outlets (8a, 8b, 9a-9d);
  Temperature adjusting means (6, 61, 62) for adjusting the temperature of air blown out from the plurality of outlets (8a, 8b, 9a-9d) into the vehicle interior;
  Temperature setting means (21, 21a, 21b) for setting the temperature in the passenger compartment;
  An internal air temperature sensor (22) for detecting the internal air temperature and an external air temperature sensor (23) for detecting the external air temperature;
  A target blowing temperature calculation unit (27 to 27) that calculates the target blowing temperature into the vehicle interior using the set temperature by the temperature setting means (21, 21a, 21b) and the temperature information detected by both sensors (22, 23) as inputs. 29b)
  As a plurality of air outlets, a foot air outlet (8a, 8b) that blows out air to the foot side of the passenger in the vehicle interior, and a face air outlet (9a to 9d) that blows out air to the upper body side of the passenger in the vehicle interior, are included.
  While adjusting the temperature adjusting means (6, 61, 62) so that the temperature of the air blown from the air outlets (8a, 8b, 9a-9d) becomes the target air temperature,
  A foot mode in which air is blown from the foot outlets (8a, 8b), a face mode in which air is blown out from the face outlets (9a to 9d), and a foot outlet ( 8a, 8b) and the vehicle air conditioner for switching the bi-level mode for blowing air from both the face outlets (9a to 9d),
  The heat exchanger (4, 5) includes a heating heat exchanger (5) for heating air using hot water as a heat source,
  A water temperature sensor (26) for detecting the temperature of the hot water and a solar radiation sensor (24) for detecting the amount of solar radiation into the room;
  Temporary target blowing temperature is input by the neural network (200) using the set temperature by the temperature setting means (21, 21a, 21b), the detected internal air temperature of the internal air temperature sensor (22) and the external air temperature detected by the external air temperature sensor (23) as inputs. A temporary target temperature calculation unit (27, 27a, 27b) for calculating (TAOB);
  Using the set temperature by the temperature setting means (21, 21a, 21b), the detected internal air temperature of the internal air temperature sensor (22), the detected external air temperature of the external air temperature sensor (23), and the detected solar radiation amount of the solar radiation sensor (24), the neural network is input. A solar radiation correction amount calculation unit (28, 28a, 28b) for calculating a solar radiation correction amount (TAOS) by the network (300);
  A target temperature calculation unit (29, 29a, 29b) for calculating a final target blowing temperature (TAO) based on the temporary target blowing temperature (TAOB) and the solar radiation correction amount (TAOS);
The target blowing temperature calculation unit (27 to 29b) includes a temporary target temperature calculation unit (27, 27a, 27b), a solar radiation correction amount calculation unit (28, 28a, 28b), and a target temperature calculation unit (29, 29a, 29b). Composed of
  The target blowing temperature is a target blowing temperature (TAO) output from the target temperature calculation unit (29, 29a, 29b),
  further,Target blowing temperature(TAO)The outlet mode for calculating the outlet mode signal by the neural network (100) using the detected outside air temperature of the outside air temperature sensor (22), the amount of solar radiation detected by the solar radiation sensor (24) and the detected water temperature of the water temperature sensor (26) as inputs. Calculation unit (31, 31a, 31b)ThePrepared,
  The air outlet switching means (11-12b) is driven and controlled by the air outlet mode signal calculated by the air outlet mode calculating section (31, 31a, 31b).
[0014]
  according to this,Vehicles in vehicle air conditionersOut of a plurality of outlets that blow out air in different directions in the room, an outlet mode for determining which air to blow out is calculated and determined by the neural network (100).
  Here, as a feature of the neural network, when a certain input signal is given, the coupling coefficient (cypnus load) between each layer in the neural network is set so that the output becomes a desired value (teacher data) set in advance. ) Is automatically corrected, by changing the teacher data under a specific input condition, and using the high-speed arithmetic device to automatically correct the coupling coefficient (cypnus load) in advance, The output can be changed under specific input conditions.
[0015]
  Moreover, in the neural network, even if the output (teacher data) is changed under the above specific input condition, the entire coupling coefficient is maintained so that a desired output value (teacher data) is maintained under other input conditions. Since the automatic correction is performed, the output change under the specific input condition does not affect the output under the other input conditions.
  As a result, the target blowing temperature,carIndoorCrewThe coupling coefficient can be modified so that the desired outlet mode can be obtained based on a specific combination with detection information of environmental factors that affect the thermal sensation of the environment. Correspondingly,carIndoorCrewA comfortable outlet mode suitable for the warmth of the room can be determined.
[0016]
In addition, it is advantageous that the coupling coefficient can be automatically corrected by the learning function of the neural network, so that a development engineer can obtain a desired output only under a specific input condition. There is no need to consider the control logic, and the development man-hours can be greatly reduced.
In addition, the use of the neural network eliminates the need for other types of control maps, complicated control logic, and the like, and thus has the advantage of reducing the capacity of a computer storage device (ROM) that constitutes the air conditioning electronic control device.
[0017]
  Affects passengers' thermal sensationClaims as environmental factor detection information1Invention describedThen, the outside air temperature detected by the outside air temperature sensor (22), the amount of solar radiation detected by the solar radiation sensor (24), and the water temperature detected by the water temperature sensor (26) are used.
  According to this, in particular,carIndoorCrewThe air outlet mode switching control can be performed in consideration of the influence of the amount of solar radiation on the air.Also,The temperature of the hot water circulating in the heat exchanger for heating (5),Outside temperature(Outdoor temperature)And usingByIn particular, in the process of rising warm water temperature at the start of air conditioning in winter,Outside temperature(Outdoor temperature)It is possible to set a comfortable air outlet mode corresponding to the change of.
[0018]
  Further, as the detection information of the environmental factor, an internal air temperature (indoor temperature) may be further added as in the invention described in claim 2. According to this, switching control of the air outlet mode can be performed in consideration of the influence of a rise in room temperature due to an increase in the amount of solar radiation, an increase in the number of passengers in the passenger compartment, and the like.
  Further, as the detection information of the environmental factor, the skin temperature of the passenger in the vehicle interior may be further added as in the third aspect of the invention. According to this, it is possible to set a comfortable air outlet mode that particularly corresponds to changes in skin temperature due to the amount of solar radiation and the like..
[0020]
In addition, the code | symbol in the parenthesis attached | subjected to each said means shows the correspondence with the specific means of embodiment description later mentioned.
[0021]
DETAILED DESCRIPTION OF THE INVENTION
DESCRIPTION OF THE PREFERRED EMBODIMENTS Embodiments shown in the drawings will be described below.
(First embodiment)
FIG. 1 shows an overview of the overall system configuration of the vehicle air conditioner according to the first embodiment. An inside / outside air switching door 1 is arranged on the most upstream side of the air flow of the vehicle air conditioner. Outside air and inside air are switched and introduced into the air duct 2.
[0022]
The air duct 2 constitutes an air passage of the air conditioner, and the blower 3, the evaporator 4 and the heater core 5 are disposed in the inside from the upstream side to the downstream side. The evaporator 4 is a cooling heat exchanger that absorbs the latent heat of evaporation of the refrigerant in the refrigeration cycle from the air and cools the air. The heater core 5 is a heating heat exchanger that heats air using hot water (engine cooling water) from a vehicle engine (not shown) as a heat source.
[0023]
An air mix door 6 is provided as a temperature adjusting means in the upstream portion of the heater core 5, and the ratio of the amount of hot air passing through the heater core 5 and the amount of cold air flowing through the bypass passage 7 of the heater core 5 is determined by the door 6. adjust. The temperature of the air blown into the passenger compartment can be adjusted by adjusting the air volume ratio of the cold / hot air.
On the most downstream side of the air duct 2 are foot outlets 8a and 8b for blowing the conditioned air toward the feet of the vehicle occupant, and the center side faces for blowing the conditioned air toward the upper body of the vehicle occupant. The blower outlets 9a-9d and the defroster blower outlet 10 for blowing an air-conditioning wind toward a windshield are provided.
[0024]
Further, on the most downstream side of the air duct 2, air outlet switching doors (air outlet switching means) 11 to 13 for selectively opening and closing the air outlets 8 a, 8 b, 9 a to 9 d and 10 are provided. By switching the open / closed state of these doors 11 to 13, a predetermined air outlet mode such as a foot mode, a bi-level mode, a face mode, and a differential mode can be set.
[0025]
Next, the control system for controlling the above-described air conditioning equipment will be described. The inside / outside air switching door 1, the air mixing door 6, and the outlet switching doors 11 to 13 are driven by servo motors 14 to 18, respectively. The operations of the servo motors 14 to 18 are controlled by the output of an air conditioning electronic control unit (hereinafter referred to as ECU) 19. Further, the motor 3 a of the blower 3 is also controlled via the motor control circuit (motor applied voltage control circuit) 20 by the output of the ECU 19.
[0026]
The amount of air blown from the blower 3 is adjusted by adjusting the motor applied voltage by the motor control circuit 20 and changing the motor rotation speed. The ECU 19 is a combination of a known microcomputer and its peripheral circuits. As an input of the ECU 19, a temperature setter (temperature setting means) 21 for setting a set temperature Tset in the passenger compartment is provided. The temperature setting device 21 is provided on the air conditioning operation panel and is manually operated.
[0027]
Further, as temperature information detecting means, an inside air sensor 22 for detecting the inside air temperature Tr in the vehicle interior and an outside air sensor 23 for detecting the outside air temperature Tam outside the vehicle compartment are provided, and further, solar radiation for detecting the amount of solar radiation Ts into the vehicle interior. A sensor 24, an evaporator temperature sensor 25 that detects the cooling temperature (blowing air temperature) Te of the evaporator 4, and a water temperature sensor 26 that detects the temperature Tw of hot water flowing into the heater core 5 are provided.
[0028]
The control function executed by the microcomputer in the ECU 19 can be roughly divided as shown in FIG. 2, and the temporary target temperature calculation unit 27 for calculating the temporary target blowing temperature TAOB is shown in FIG. The temperature setting signal Tset, the inside air temperature sensor signal Tr, and the outside air temperature sensor signal Tam are input and the neural network 200 calculates a temporary target blowing temperature TAOB.
[0029]
Further, the solar radiation correction amount calculation unit 28 for calculating the solar radiation correction amount TAOS is constituted by the neural network 300 shown in FIG. 6, and includes a temperature setting signal Tset, an internal air temperature sensor signal Tr, an external air temperature sensor signal Tam, and solar radiation. Using the sensor signal Ts as an input, the solar radiation correction amount TAOS is calculated by the neural network 300. And the target temperature calculation part 29 calculates the target blowing temperature TAO finally based on the output of the temporary target temperature calculation part 27 and the solar radiation correction amount calculation part 28. FIG. Further, the air mix door opening degree calculation unit 30 calculates the air mix door opening degree SW based on the output TAO of the target temperature calculation unit 29.
[0030]
Further, the air outlet mode calculating unit 31 for calculating the air outlet mode signal TMODE is constituted by the neural network 100 shown in FIG. 3, and the target air outlet temperature TAO from the target temperature calculating unit 29 and the temperature of the passenger in the passenger compartment. The solar radiation sensor signal Ts, the outside air temperature sensor signal Tam, and the water temperature sensor signal Tw are input as detection information of environmental factors that affect the feeling, and the air outlet mode signal TMODE is calculated by the neural network 100.
[0031]
The air volume calculation unit 32 includes the neural network 400 shown in FIG. 7, and receives the temperature setting signal Tset, the inside air temperature sensor signal Tr, the outside air temperature sensor signal Tam, and the solar radiation sensor signal Ts as inputs. The blower voltage level TBLO for determining the air volume by 400 is calculated.
Next, the outline of the neural network will be described. Since the neural networks 100 to 400 basically have the same configuration, the neural network 100 in FIG. 3 will be described as an example. The neural network is configured so that when a certain input signal (TAO, Ts, Tam, Tw in the example of FIG. 3) is given, the output becomes a predetermined value (teacher data) set in advance. An error back-propagation learning function (back) that corrects the coupling coefficient (cypnus load) 106 between the neurons 105 in the input layer 101, the first and second intermediate layers 102 and 103, and the output layer 104 provided in 100. This is a hierarchical network with a proper permeation function.
[0032]
Then, when the teacher data is changed, the coupling coefficient (cypnus load) 106 is corrected by repeatedly “learning” so that the output for a certain input signal becomes the changed teacher data again. That is, the correlation function (coupling coefficient 106) is automatically generated from a large amount of data (teacher data). As the teacher data, a desired value (a desired output value with respect to the input signal) obtained by an experiment or the like is set.
[0033]
In the hierarchical neural network 100, there is no connection between the neurons 105 in the same layer, and only the neurons 105 in the previous and subsequent layers are connected, and the connection coefficient 106 between the neurons 105 in each layer is the weight of each connection. This indicates the degree of (strength), and as the connection weight increases, the signal of the neuron 105 in the front layer becomes a signal having a larger amplitude and is transmitted to the neuron 105 in the rear layer.
[0034]
The input / output values are obtained by standardizing (normalizing) the sensor signals and the like from 0 to 1, and the actually output values need to be inversely converted from 0 to 1. For example, the actual detection range of the internal air temperature Tr detected by the internal air sensor 22 is normally 0 ° C. to 50 ° C., and this detection value is assigned to 0 to 1 by the normalization unit 107 and input to the neural network. Input to layer 101. Since the output result from the output layer 104 is also a value from 0 to 1, an actual value corresponding to a sensor signal or the like corresponding to a sensor signal or the like by a conversion map preset in the output conversion unit 108 in the neural networks 200 to 400 of FIGS. Inverted to value. However, in the neural network 100 of FIG. 3, since the output is the air outlet mode signal TMODE, it is not necessary to reversely convert the output result from the output layer 104, and therefore the output conversion unit 108 is not provided.
[0035]
By the way, since there are various environmental conditions facing the current vehicle air conditioner, there are several tens of thousands of teacher data that are desired output values (for example, air outlet mode signals) corresponding to these various environmental conditions. Over 100,000 points and a huge number.
Therefore, when designing the ECU 19, a dedicated high-speed arithmetic device is used as a pre-stage process for mounting on the vehicle, and the high-speed arithmetic device performs learning using the neural network 100 in FIG. Thus, the coupling coefficient 106 whose output is the desired teacher data is calculated. Then, the coupling coefficient 106 calculated in this way is stored in a storage unit (ROM) corresponding to the neural network 100, 200, 300, 400 of each calculation unit in the ECU 19 in FIG.
[0036]
Therefore, in the vehicle-mounted state, the coupling coefficient 106 between the neurons 105 in each layer in the neural networks 100 to 400 of the calculation units in the ECU 19 is a predetermined value set in advance.
Then, in the vehicle mounted state, the neural network 100 of each calculation unit in the ECU 19 calculates an output with respect to the input as shown in FIG. That is, in each neuron 105, the input signal 0₁~ O_nCorresponding to the coupling coefficient 106 (W₁~ W_n) And apply the value to a function called a sigmoid function to calculate the output. The calculation result is output as the input of the subsequent neuron. Repeat this to get the final output.
[0037]
In the neural network 100 of each calculation unit in the ECU 19 mounted in the vehicle, the input signal 0₁~ O_nThe coupling coefficient 106 (W) for obtaining a desired output value (teacher signal) corresponding to each change in a wide range₁~ W_n) Is set in advance, learning for correcting the coupling coefficient is not necessary, and only the calculation shown in FIG.
[0038]
Therefore, in the neural network 100 of the air outlet mode calculation unit 31 shown in FIG. 3, each of the desired values (teacher signals) set in advance corresponding to the change of the input signals (TAO, Ts, Tam, Tw) is obtained. ) As the outlet mode signal TMODE (= 0 to 1) and output.
In addition, in the neural network 200 of the temporary target temperature calculation unit 27 shown in FIG. 5, in response to changes in the input signals (Tset, Tr, Tam), predetermined desired values (teacher signals) are respectively set. Calculated and output as a temporary target blowing temperature TAOB.
[0039]
Further, in the neural network 300 of the solar radiation correction amount calculation unit 28 shown in FIG. 6, each of the desired values (teacher signals) set in advance corresponding to the change of the input signals (Tset, Tr, Tam, Ts) is obtained. ) Is calculated and output as the solar radiation correction amount TAOS.
Further, in the neural network 400 of the air volume calculation unit 32 shown in FIG. 7, desired values (teacher signals) set in advance are respectively set in response to changes in the input signals (Tset, Tr, Tam, Ts). Calculate and output as blower voltage level TBLO.
[0040]
And in the target temperature calculation part 29, the final target blowing temperature TAO is calculated by the following numerical formula 2.
[0041]
[Expression 2]
TAO = TAOB-TAOS
Next, in the air mix door opening degree calculation unit 30, the air mix door opening degree is calculated by the following Equation 3 based on the output TAO of the target temperature calculation unit 29, the temperature Te of the evaporator 4, and the hot water temperature Tw of the heater core 5. SW is calculated.
[0042]
[Equation 3]
SW (%) = (TAO−Te) / (Tw−Te) * 100
Next, a control example according to this embodiment will be described with reference to the flowchart of FIG. The control routine of FIG. 8 is started by an operation switch signal for starting the air conditioner. In step 510, the air conditioning ECU 19 is reset. In step 520, the signals of the various sensors 22 to 26 such as the internal temperature Tr, the external temperature Tam, and the like. The signal of the temperature setting device 21 is read.
[0043]
Next, in step 530, the temporary target temperature TAOB is calculated using the temporary target temperature neural network 200 shown in FIG. Therefore, step 530 corresponds to the temporary target temperature calculation unit 27 in FIG.
Next, in step 540, the solar radiation correction amount TAOS is calculated using the solar radiation correction amount neural network 300 shown in FIG. Therefore, step 540 corresponds to the solar radiation correction amount calculation unit 28 of FIG.
[0044]
Next, in step 550, the final target blowing temperature TAO is calculated by the above-described equation 1. Therefore, step 550 corresponds to the target temperature calculation unit 29 in FIG.
Next, in step 560, the air mix door opening degree SW is calculated by the above-described formula 2. Therefore, step 560 corresponds to the air mix door opening degree calculation unit 30 in FIG.
[0045]
Next, in step 570, the air outlet mode signal TMODE is calculated using the air outlet mode neural network 100 shown in FIG. Therefore, step 570 corresponds to the outlet mode calculation unit 31 in FIG. Note that the output value of the outlet mode signal TMODE in step 570 has a characteristic that increases as the target outlet temperature TAO shifts from the low temperature side to the high temperature side. Based on the output value TMODE of the air outlet mode neural network 300, the face (FACE), bi-level (B / L), and foot (FOOT) modes are determined as shown in FIG.
[0046]
Next, in step 580, the target blower voltage TBLO is calculated using the air volume calculation neural network 400 shown in FIG. Therefore, step 580 corresponds to the air volume calculation unit 32 of FIG.
Next, in steps 590 to 610, the actuators (motors 14 to 18 in FIG. 1) and the blower motor applied voltage control circuit 20 are driven and controlled so as to coincide with the target values obtained previously.
[0047]
Next, the characteristic by calculating the blower outlet mode signal TMODE using the neural network 100 like this embodiment is demonstrated concretely.
FIG. 12 is a chart showing the relationship between the inputs 1 to 4 and the output (teacher data) TMODE in the air outlet mode neural network 100. The inputs 1 to 4 are TAO = 48 ° C. and Ts = 1000 W / m, respectively.²When Tam = 0 ° C and Tw = 80 ° C (ie, when there is solar radiation Ts and the outside air temperature Tam is low), if the output is 0.95, as shown in FIG. The air outlet mode becomes foot mode, and the occupant feels a sense of heat on the head side.
[0048]
Therefore, the output (teacher data) under the above input condition is changed from 0.95 to 0.5.
Here, as a feature of the neural network, when a certain input signal is given, the coupling coefficient (cypnus load) between each layer in the neural network is set so that the output becomes a desired value (teacher data) set in advance. ) 106 has a learning function of automatically correcting 106, the teacher data under the specific input condition is changed, and the correction of the coupling coefficient (cypnus load) 106 is performed in advance using a high-speed arithmetic device. Thus, the output can be changed.
[0049]
As a result of the change in the output (change from TMODE = 0.95 to 0.5), as shown in FIG. 11B, even if the target blowing temperature TAO is the same value a (= 48 ° C.), The exit mode becomes the bi-level mode, and it is possible to blow cool air toward the passenger's head side, which can reduce the feeling of burning of the passenger's head due to solar radiation and improve the air conditioning feeling of the passenger.
[0050]
Moreover, even if the output (teacher data) is changed under the specific input condition, the entire coupling coefficient 106 is automatically corrected so that the desired output value (teacher data) is maintained under the other input conditions. Therefore, the output change under the specific input condition does not affect the output under other input conditions. As a result, under the condition of no solar radiation, the foot mode shown in FIG. 11 (a) can be set, and the feeling of heating at the occupant's feet can be improved by blowing hot air toward the occupants' feet.
[0051]
Furthermore, it is advantageous that the coupling coefficient 106 can be automatically corrected by the learning function of the neural network, so that the development engineer can obtain a desired output only under a specific input condition. It is not necessary to consider the control logic, and the development man-hour can be greatly reduced.
In addition, the adoption of the neural network eliminates the need for complicated control logic and various types of control maps, and thus has an advantage that the ROM capacity in the in-vehicle ECU 19 can be reduced.
[0052]
As shown in FIG. 11 (b), when the bi-level mode is set under the condition of solar radiation at low outside air temperature, an upper limit is set on the air mix door opening as shown in FIG. 11 (c). It is preferable to provide (a door opening limiter setting).
That is, in FIG. 11C, in the bi-level mode expansion region where TAO = a or more, the actual blown air temperature into the passenger compartment is suppressed to a predetermined temperature by the upper limit setting (limiter setting) of the air mix door opening. It is necessary to prevent hot air from blowing out from the face outlets 9a to 9d. In the bi-level mode of FIG. 11 (c), b is the face blowing temperature, and c is the foot blowing temperature.
[0053]
Next, when the air conditioner is started immediately after starting the vehicle engine under the low outdoor temperature condition in winter, the switching control of the air outlet mode will be described. After the vehicle engine starts, the engine coolant temperature (Hot water temperature to the heater core 5) rises, and accordingly, the blown air temperature of the heater core 5 and consequently the blown temperature into the passenger compartment rises. At that time, the motor applied voltage of the blower 3 is adjusted so that the amount of air blown into the passenger compartment also increases as the hot water temperature increases.
[0054]
At this time, if the foot mode remains fixed as the blowing mode into the passenger compartment, the occupant is warmed from the lower half of the body, and thus it takes a very long time to warm up to the occupant upper half. As a result, the passenger's hand is particularly cold, which is not only uncomfortable but also difficult for the driver to operate the steering wheel.
[0055]
Therefore, the blow mode to the passenger compartment is initially started in the foot mode, and then the bi-level mode is set as the hot water temperature rises, and the warm air from the face outlets 9a to 9d is also sent to the upper body side of the occupant. It is desired to heat the occupant's upper body side early by blowing it out. Note that the maximum heating state is set at the start of air conditioning at low outside air temperature, the air mix door opening SW is at the maximum opening (100% opening), and the ventilation path to the heater core 5 is fully opened.
[0056]
When the air conditioner is started under the low outside air temperature condition in winter, the present inventors have actually experimented on the condition that the occupant feels comfortable in the bi-level mode. As shown in FIG. The area has a correlation between the outside air temperature and the hot water temperature, and it has been found that there is a hot water temperature range in which the bi-level mode is comfortable for each outside air temperature.
[0057]
That is, in the experiment of FIG. 13, whether or not the bi-level mode under the above conditions is comfortably determined is determined by a plurality of monitors, and the hot water temperature range in which the bi-level mode is comfortably felt as the outside air temperature decreases. Can be seen to rise. In FIG. 13, the region between the cold region and the comfortable region, and the region between the comfortable region and the hot region are intermediate regions that are neither comfortable nor uncomfortable. Further, the actual temperature of the air blown into the passenger compartment is approximately 90% of the hot water temperature due to the heat transfer efficiency between the hot water and the air in the heater core 5.
[0058]
In response to the experimental results shown in FIG. 13, in this embodiment, as shown in FIG. 14, the input 1 to input 4 and the output (teacher data) TMODE in the outlet mode neural network 100 are input 1 to 1. Input 3 is TAO = 80 ° C, Ts = 0W / m²When Tam = −10 ° C. and the input 4 is in the range of Tw = 53 ° C. to 62 ° C., the output is changed from 0.95 to 0.5. Therefore, the air outlet mode can be changed from the foot mode to the bi-level mode, and the upper body side of the occupant can be heated early within the range of Tw, thereby improving air conditioning feeling and improving vehicle safety. .
[0059]
In other hot water temperature ranges, the output can be maintained at 0.95 and the outlet mode can be set to the foot mode, so the foot part is cold due to the bi-level mode at the low temperature side of the hot water temperature, or the high temperature side of the hot water temperature This prevents the face from burning in the bi-level mode.
(Second Embodiment)
In the first embodiment, the bi-level mode is set in a predetermined hot water temperature range when starting the air conditioner under the low outdoor temperature condition in winter, but the internal temperature Tr is somewhat high due to solar radiation or the like. If the timing for returning from the bi-level mode to the foot mode is not advanced, a feeling of burning of the face due to the bi-level mode occurs.
[0060]
Therefore, in the second embodiment, in consideration of this point, as shown in FIG. 15, an internal air temperature Tr is added as an input to the air outlet mode neural network 100, and the internal air temperature Tr is increased to a predetermined temperature or higher. The timing for returning from the bi-level mode to the foot mode is advanced to prevent the occurrence of a hot feeling on the face. That is, even if it is the same outside temperature, if the inside temperature Tr rises, the hot water temperature returned from the bi-level mode to the foot mode is changed to a lower value.
[0061]
(Third embodiment)
The third embodiment has the same purpose as that of the second embodiment. As shown in FIG. 16, the skin temperature of the occupant is used as an input to the air outlet mode neural network 100 instead of the internal temperature Tr. A skin temperature signal Th from the skin temperature sensor to be detected is added.
[0062]
According to the third embodiment, when the occupant's skin temperature rises to a predetermined temperature or more due to the influence of solar radiation or the like, the hot water temperature for returning from the bilevel mode to the foot mode is changed to a lower temperature, thereby A feeling of fire can be prevented.
(Fourth embodiment)
FIG. 17 shows the fourth embodiment. As shown in FIG. 3, when the outside air temperature Tam is added as one of the inputs of the air outlet mode neural network 100, the air outlet is changed depending on the level of the outside air temperature Tam. This is an example in which the mode switching point is changed. In other words, in the high temperature side area (heating side area) of TAO, the TAO is lower at low outside air temperature (Tam = −10 ° C.) than at high outside air temperature (Tam = −10 ° C.). The foot mode area is expanded by switching from mode to foot mode. Thereby, foot heating is performed preferentially and the heating feeling at the time of low outside temperature is raised.
[0063]
Further, in the low temperature side area (cooling side area) of TAO, the face mode is set until the TAO becomes higher at high outside air temperature (Tam = 30 ° C.) than at low outside air temperature (Tam = 10 ° C.). Continue to expand the face mode area. This preferentially blows out cool air to the upper body of the occupant to enhance the cooling feeling at high outside temperatures.
[0064]
(Fifth embodiment)
In the first to fourth embodiments described above, one air passage is formed in the air duct 2 toward the air outlets 8a, 8b, 9a to 9d and 10 as shown in FIG. In the fifth embodiment, as shown in FIG. 18, the temperatures of the driver's seat side air conditioning zone and the passenger seat side air conditioning zone are independently controlled in the fifth embodiment. The present invention is applied to the left and right independent temperature control type vehicle air conditioner.
[0065]
In the fifth embodiment, a partition wall 2a is installed in the air duct 2 from the heater core 5 portion toward the downstream side, and the partition wall 2a causes the passage in the air duct 2 to be a driver seat side passage 2b and a passenger seat side passage 2c. It is divided into and.
A driver-seat-side air mix door 61 is provided upstream of the heater core 5 in the driver-seat-side passage 2b, and flows in the driver-seat-side passage 2b bypassing the heater core 5 and the amount of warm air passing through the heater core 5. The ratio of the cool air volume is adjusted by the door 61. Further, in the passenger seat side passage 2c, a passenger seat side air mix door 62 is provided upstream of the heater core 5, and the amount of warm air passing through the heater core 5 in the passenger seat side passage 2c and the heater core 5 are bypassed. The ratio of the cold air volume is adjusted by the door 62.
[0066]
A driver seat side foot outlet 8a and face outlets 9a and 9b are provided on the most downstream side of the driver seat side passage 2b, and a passenger seat side foot outlet is provided on the most downstream side of the passenger seat side passage 2c. An outlet 8b and face outlets 9c and 9d are provided. Further, there are provided air outlet switching doors 11a and 12a for selectively opening and closing the foot air outlet 8a and the face air outlets 9a and 9b on the driver's seat side, and the foot air outlet 8b and the face air outlet on the passenger seat side. Air outlet switching doors 11b and 12b for selectively opening and closing 9c and 9d are provided. The defroster outlet 10 and the outlet switching door 13 are the same as those in the first embodiment.
[0067]
Both the air mix doors 61 and 62 are driven by independent servo motors 15 and 15a, respectively, and the air outlet switching doors 11a and 12a on the driver's seat side and the air outlet switching doors 11b and 12b on the passenger seat side are Driven by independent servo motors 160 and 170, respectively. And by switching the open / closed state of the air outlet switching doors 11a, 12a, 11b, 12b, predetermined air outlet modes such as a foot mode, a bi-level mode, and a face mode are set independently for each passage 2b, 2c. obtain.
[0068]
Further, as an input of the ECU 19, a driver seat side temperature setting device (first temperature setting means) 21a for setting a set temperature Tset (Dr) of the driver seat side air conditioning zone corresponding to the driver seat side passage 2b, and a passenger seat A passenger seat side temperature setter (second temperature setting means) 21b for setting the set temperature Tset (Pa) of the passenger seat side air conditioning zone corresponding to the side passage 2c is provided independently.
[0069]
Further, a driver seat side solar radiation sensor 24a for detecting the solar radiation amount TsDr to the driver seat side air conditioning zone and a passenger seat side solar radiation sensor 24b for detecting the solar radiation amount TsPa to the passenger seat side air conditioning zone are provided independently. The inside air sensor 22, the outside air sensor 23, the evaporator temperature sensor 25, and the water temperature sensor 26 as temperature information detecting means are the same as those in the first embodiment.
[0070]
Further, as shown in FIG. 19, the control function executed by the microcomputer in the ECU 23 is independently performed on the driver seat side Dr and the passenger seat side Pa. In FIG. 2, the subscript a attached to the control function unit is the driver side Dr, the subscript b attached is the passenger side Pa, and the blower voltage TBLO for determining the air volume is determined on the driver side. After calculating the blower voltage TBLO (Dr) and the passenger seat side blower voltage TBLO (Pa) by the air volume calculation units 32a and 32b, the air volume calculation unit 32c calculates the average value of the blower voltages TBLO (Dr) and TBLO (Pa). This is calculated and used as the final blower voltage TBLO corresponding to the air volume.
[0071]
In addition, air outlet mode calculation units 31a and 31b for independently calculating the air outlet mode signal TMODE (Dr) on the driver's seat side and the air outlet mode signal TMODE (Pa) on the passenger seat side are provided independently.
In this case, in the neural network 100 constituting the driver seat side outlet mode calculating unit 31a and the passenger seat side outlet mode calculating unit 31b, the driver seat side target outlet temperature is used as the target outlet temperature TAO of FIG. TAO (Dr) or the passenger side target blowing temperature TAO (Pa) is input, and the driver side solar radiation amount TsDr or the passenger side solar radiation amount TsPa is input as the solar radiation amount Ts. The outlet mode signal TMODE (Dr) or the passenger side side outlet mode signal TMODE (Pa) may be calculated independently.
[0072]
In the neural network 200 constituting the driver's seat side temporary target temperature calculation unit 27a and the passenger's side temporary target temperature calculation unit 27b, the set temperature Tset of the driver's seat side air conditioning zone is used as the input (Tset) in FIG. (Dr) or the set temperature Tset (Pa) of the passenger side air conditioning zone is input, and the difference (ΔTset) between the set temperatures Tset (Dr) and Tset (Pa) is added as an input. The reason why the set temperature difference ΔTset is added as an input is to suppress a temperature difference between the zones due to temperature interference between the driver side air conditioning zone and the passenger side air conditioning zone.
[0073]
Further, in the vehicle air conditioner of the left and right independent temperature control type as in the fifth embodiment, the air outlet mode may be the same on the driver seat side and the passenger seat side without independent control. In this case, as shown in FIG. 20, as an input to the neural network 100, the average value TAOX of the driver's seat side target blowing temperature TAO (Dr) and the passenger's seat side target blowing temperature TAO (Pa), and the driver's seat side solar radiation amount The average value TsX between TsDr and the passenger side solar radiation amount Pa may be input to calculate the air outlet mode signal TMODE.
[0074]
(Other embodiments)
(1) In the above-described embodiments, the case where the target blowing temperature and the air volume (blower voltage level) are calculated by the respective neural networks 200, 300, and 400 has been described. The calculation may be performed by a known method without using a neural network.
[0075]
(2) In the above-described embodiment, the case where the air mix doors 6, 61, 62 for adjusting the air volume ratio between the cold air and the warm air are provided as the temperature adjusting means. However, the air mix doors 6, 61 are used as the temperature adjusting means. Instead of 62, a hot water valve for controlling the flow rate or temperature of the hot water flowing into the heater core 5 may be used.
(3) In the vehicle air conditioner of the left and right independent temperature control system according to the fifth embodiment described above, in the example shown in FIG. 20, as the input to the air outlet mode neural network 100, the driver's seat side target air outlet temperature TAO (Dr) and The average value TAOX with the passenger side target blowing temperature TAO (Pa) is used, but the weighting of the driver seat side target blowing temperature TAO (Dr) and the passenger seat side target blowing temperature TAO (Pa) is changed, for example, The target blowing temperature TAO in which the influence ratio between the driver's seat side target blowing temperature TAO (Dr) and the passenger's seat side target blowing temperature TAO (Pa) is 80% and the other is 20% may be input.
[0076]
(4) Needless to say, the temperature setting devices 21, 21a, 21b for setting the temperature of the air-conditioning zone may be those of a warm feeling display that does not indicate temperature numbers (high and low temperature color-coded display, etc.).
(5) Although the hot water temperature is detected as an environmental factor that affects the blowout temperature during maximum heating, since the hot water temperature and the surface temperature of the heater core 5 are closely correlated, The surface temperature of the heater core 5 may be detected.
[0077]
Further, a temperature sensor that detects the temperature of the air blown from the heater core 5 can be used instead of the water temperature sensor 26.
(6) The present invention is not limited to a vehicle air conditioner, and can be applied to various uses as long as the air conditioner requires switching control of the air outlet mode.
[Brief description of the drawings]
FIG. 1 is an explanatory diagram of an overall system of a vehicle air conditioner showing a first embodiment of the present invention.
2 is a block explanatory diagram of main functions in the air-conditioning electronic control device of FIG. 1; FIG.
FIG. 3 is a schematic configuration diagram of a neural network of the outlet mode calculation unit in FIG. 2;
FIG. 4 is an explanatory diagram of an output calculation method of a neural network.
5 is a schematic configuration diagram of a neural network of a temporary target temperature calculation unit in FIG. 2;
6 is a schematic configuration diagram of a neural network of the solar radiation correction amount calculation unit of FIG. 2;
7 is a schematic configuration diagram of a neural network of the air volume calculation unit of FIG. 2;
FIG. 8 is a control flowchart according to the first embodiment of the present invention.
FIG. 9 is a characteristic diagram of air outlet mode calculation in the first embodiment of the present invention.
FIG. 10 is an explanatory diagram of a conventional outlet mode switching control characteristic.
FIG. 11 is an explanatory diagram of the air outlet mode switching control characteristics according to the prior art and the first embodiment.
FIG. 12 is a chart showing a relationship between input conditions and the output of the air outlet mode signal according to the first embodiment.
FIG. 13 is a graph showing the relationship between the comfort in the bi-level mode and the outside air temperature and hot water temperature in the first embodiment.
FIG. 14 is a chart showing the relationship between the input conditions and the output of the air outlet mode signal according to the first embodiment.
FIG. 15 is a schematic configuration diagram of a neural network of an outlet mode calculation unit according to a second embodiment.
FIG. 16 is a schematic configuration diagram of a neural network of an outlet mode calculation unit according to a third embodiment.
FIG. 17 is a control characteristic diagram showing the relationship between the outlet mode and the target outlet temperature according to the fourth embodiment.
FIG. 18 is an explanatory diagram of an entire system of a vehicle air conditioner showing a fifth embodiment.
19 is a block explanatory diagram of main functions in the air-conditioning electronic control device of FIG. 18;
FIG. 20 is a schematic configuration diagram illustrating an example of a neural network of the outlet mode calculation unit according to the fifth embodiment.
[Explanation of symbols]
2 ... Air duct (air passage), 2b ... Driver seat side air passage,
2c ... Driver side air passage, 6, 61, 62 ... Temperature adjusting means,
8a, 8b, 9a to 9d ... outlet, 21, 21a, 21b ... temperature setting means,
22, 23 ... Temperature information detecting means, 31, 31a, 31b ... Outlet mode calculating unit, 100-400 ... Neural network.

Claims (3)

An air passage (2, 2b, 2c) having a heat exchanger (4, 5) for exchanging heat with air;
A plurality of air outlets (8a, 8b, 9a to 9d) that are provided on the downstream side of the air passages (2, 2b, 2c) and blow out air in different directions in the vehicle interior;
Outlet switching means (11-12b) for switching opening and closing of the plurality of outlets (8a, 8b, 9a-9d);
Temperature adjusting means (6, 61, 62) for adjusting the temperature of the air blown out from the air outlets (8a, 8b, 9a-9d) into the vehicle interior;
Temperature setting means (21, 21a, 21b) for setting the temperature in the passenger compartment;
An internal air temperature sensor (22) for detecting the internal air temperature and an external air temperature sensor (23) for detecting the external air temperature;
A target blowing temperature calculation unit (calculating a target blowing temperature into the vehicle interior) using the set temperature set by the temperature setting means (21, 21a, 21b) and the temperature information detected by the sensors (22, 23) as inputs. 27-29b),
The plurality of air outlets include a foot air outlet (8a, 8b) that blows air toward the feet of the passenger in the vehicle interior and a face air outlet (9a to 9d) that blows air toward the upper body side of the passenger in the vehicle interior. ,
While adjusting the temperature adjusting means (6, 61, 62) so that the temperature of the air blown from the air outlets (8a, 8b, 9a-9d) becomes the target air temperature,
A foot mode in which the air outlet switching means (11-12b) is driven and controlled to blow air out of the foot air outlets (8a, 8b), a face mode in which air is blown out from the face air outlets (9a-9d), and In the vehicle air conditioner for switching the bi-level mode for blowing air from both the foot outlet (8a, 8b) and the face outlet (9a-9d),
The heat exchanger (4, 5) includes a heating heat exchanger (5) for heating air using hot water as a heat source,
A water temperature sensor (26) for detecting the temperature of the hot water and a solar radiation sensor (24) for detecting the amount of solar radiation into the passenger compartment ;
Using the temperature set by the temperature setting means (21, 21a, 21b), the detected internal air temperature of the internal air temperature sensor (22), and the external air temperature detected by the external air temperature sensor (23) as inputs, the neural network (200) A temporary target temperature calculation unit (27, 27a, 27b) for calculating a target blowing temperature (TAOB);
The set temperature by the temperature setting means (21, 21a, 21b), the detected internal temperature of the internal temperature sensor (22), the detected external temperature of the external temperature sensor (23), and the detected solar radiation amount of the solar sensor (24). As an input, a solar radiation correction amount calculation unit (28, 28a, 28b) for calculating a solar radiation correction amount (TAOS) by the neural network (300);
A target temperature calculator (29, 29a, 29b) for calculating a final target outlet temperature (TAO) based on the temporary target outlet temperature (TAOB) and the solar radiation correction amount (TAOS);
The target blowing temperature calculation unit (27 to 29b) includes the temporary target temperature calculation unit (27, 27a, 27b), the solar radiation correction amount calculation unit (28, 28a, 28b), and the target temperature calculation unit (29, 29a). 29b),
The target blowing temperature is a target blowing temperature (TAO) output from the target temperature calculation unit (29, 29a, 29b),
Further, the neural network (100 ) receives the target blowing temperature (TAO) , the detected outside air temperature of the outside air temperature sensor (22), the detected solar radiation amount of the solar radiation sensor (24), and the detected water temperature of the water temperature sensor (26). ) Is provided with an outlet mode calculation unit (31, 31a, 31b) for calculating an outlet mode signal.
An air conditioner for vehicles, wherein the air outlet switching means (11-12b) is drive-controlled by the air outlet mode signal calculated by the air outlet mode calculating section (31, 31a, 31b). The detected internal air temperature of the internal air temperature sensor (22) is further input as an input to the neural network (100) of the outlet mode calculation unit (31, 31a, 31b) . Vehicle air conditioner. A skin temperature sensor for detecting the skin temperature of the indoor user is provided, and the detected skin temperature of the skin temperature sensor (22) is input as an input to the neural network (100) of the outlet mode calculation unit (31, 31a, 31b). The vehicle air conditioner according to claim 1, further inputted.

Images